{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/adam/papers/78","list_of":"/method/adam","method":"Adam","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":78,"pages_in_order":244,"rows_per_page":100,"rows":[7701,7800],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/adam","prev":"/method/adam/papers/77","next":"/method/adam/papers/79","papers":[{"paper":"/paper/deblurdinat-a-lightweight-and-effective","slug":"deblurdinat-a-lightweight-and-effective","title":"DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains","date":"2024-03-19","arxiv_id":"2403.13163","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-driven-self-supervised-learning-for","slug":"diffusion-driven-self-supervised-learning-for","title":"Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation","date":"2024-03-19","arxiv_id":"2403.12728","n_code_links":1,"syntology":null},{"paper":"/paper/emotion-recognition-using-transformers-with","slug":"emotion-recognition-using-transformers-with","title":"Emotion Recognition Using Transformers with Masked Learning","date":"2024-03-19","arxiv_id":"2403.13731","n_code_links":1,"syntology":null},{"paper":"/paper/encode-once-and-decode-in-parallel-efficient","slug":"encode-once-and-decode-in-parallel-efficient","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","date":"2024-03-19","arxiv_id":"2403.13112","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-pre-trained-language-models-to","slug":"fine-tuning-pre-trained-language-models-to","title":"Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks","date":"2024-03-19","arxiv_id":"2403.15458","n_code_links":0,"syntology":null},{"paper":"/paper/flowerformer-empowering-neural-architecture","slug":"flowerformer-empowering-neural-architecture","title":"FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer","date":"2024-03-19","arxiv_id":"2403.12821","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["y0ngjaenius/cvpr2024_flowerformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graphere-jointly-multiple-event-event","title":"GraphERE: Jointly Multiple Event-Event Relation Extraction via Graph-Enhanced Event Embeddings","date":"2024-03-19","arxiv_id":"2403.12523","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-eatformer-a-vision-transformer-for","title":"Improved EATFormer: A Vision Transformer for Medical Image Classification","date":"2024-03-19","arxiv_id":"2403.13167","n_code_links":0,"syntology":null},{"paper":"/paper/insight-end-to-end-neuro-symbolic-visual","slug":"insight-end-to-end-neuro-symbolic-visual","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","date":"2024-03-19","arxiv_id":"2403.12451","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["liruiluo/nsrl-vision-pub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructing-large-language-models-to-identify","slug":"instructing-large-language-models-to-identify","title":"Instructing Large Language Models to Identify and Ignore Irrelevant Conditions","date":"2024-03-19","arxiv_id":"2403.12744","n_code_links":1,"syntology":null},{"paper":null,"slug":"lhmke-a-large-scale-holistic-multi-subject","title":"LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models","date":"2024-03-19","arxiv_id":"2403.12601","n_code_links":0,"syntology":null},{"paper":"/paper/llmlingua-2-data-distillation-for-efficient","slug":"llmlingua-2-data-distillation-for-efficient","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","date":"2024-03-19","arxiv_id":"2403.12968","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-fusion-method-with-spatiotemporal","title":"Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation","date":"2024-03-19","arxiv_id":"2403.12425","n_code_links":0,"syntology":null},{"paper":null,"slug":"pipelined-biomedical-event-extraction","title":"Pipelined Biomedical Event Extraction Rivaling Joint Learning","date":"2024-03-19","arxiv_id":"2403.12386","n_code_links":0,"syntology":null},{"paper":"/paper/pragmatic-competence-evaluation-of-large","slug":"pragmatic-competence-evaluation-of-large","title":"Pragmatic Competence Evaluation of Large Language Models for the Korean Language","date":"2024-03-19","arxiv_id":"2403.12675","n_code_links":1,"syntology":null},{"paper":null,"slug":"rankprompt-step-by-step-comparisons-make","title":"RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners","date":"2024-03-19","arxiv_id":"2403.12373","n_code_links":0,"syntology":null},{"paper":"/paper/seven-pruning-transformer-model-by-reserving","slug":"seven-pruning-transformer-model-by-reserving","title":"SEVEN: Pruning Transformer Model by Reserving Sentinels","date":"2024-03-19","arxiv_id":"2403.12688","n_code_links":1,"syntology":null},{"paper":null,"slug":"simple-hack-for-transformers-against-heavy","title":"Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Service","date":"2024-03-19","arxiv_id":"2403.12563","n_code_links":0,"syntology":null},{"paper":null,"slug":"tt-blip-enhancing-fake-news-detection-using","title":"TT-BLIP: Enhancing Fake News Detection Using BLIP and Tri-Transformer","date":"2024-03-19","arxiv_id":"2403.12481","n_code_links":0,"syntology":null},{"paper":null,"slug":"videobadminton-a-video-dataset-for-badminton","title":"Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset","date":"2024-03-19","arxiv_id":"2403.12385","n_code_links":0,"syntology":null},{"paper":"/paper/vl-icl-bench-the-devil-in-the-details-of","slug":"vl-icl-bench-the-devil-in-the-details-of","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","date":"2024-03-19","arxiv_id":"2403.13164","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ys-zong/vl-icl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-disease-labeler-for-chinese-chest-x-ray","title":"A Disease Labeler for Chinese Chest X-Ray Report Generation","date":"2024-03-18","arxiv_id":"2404.16852","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-continuous-emotion-recognition-with","title":"Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers","date":"2024-03-18","arxiv_id":"2403.11440","n_code_links":0,"syntology":null},{"paper":"/paper/cicle-conformal-in-context-learning-for","slug":"cicle-conformal-in-context-learning-for","title":"CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification","date":"2024-03-18","arxiv_id":"2403.11904","n_code_links":1,"syntology":null},{"paper":null,"slug":"compositional-learning-of-functions-in-humans","title":"Compositional learning of functions in humans and machines","date":"2024-03-18","arxiv_id":"2403.12201","n_code_links":0,"syntology":null},{"paper":null,"slug":"construction-of-hyper-relational-knowledge","title":"Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models","date":"2024-03-18","arxiv_id":"2403.11786","n_code_links":0,"syntology":null},{"paper":"/paper/continual-forgetting-for-pre-trained-vision","slug":"continual-forgetting-for-pre-trained-vision","title":"Continual Forgetting for Pre-trained Vision Models","date":"2024-03-18","arxiv_id":"2403.11530","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["bjzhb666/GS-LoRA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/counting-stars-a-simple-efficient-and","slug":"counting-stars-a-simple-efficient-and","title":"Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models","date":"2024-03-18","arxiv_id":"2403.11802","n_code_links":1,"syntology":null},{"paper":null,"slug":"crystalformer-infinitely-connected-attention","title":"Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding","date":"2024-03-18","arxiv_id":"2403.11686","n_code_links":0,"syntology":null},{"paper":"/paper/easyjailbreak-a-unified-framework-for","slug":"easyjailbreak-a-unified-framework-for","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","date":"2024-03-18","arxiv_id":"2403.12171","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["easyjailbreak/easyjailbreak"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"embracing-the-generative-ai-revolution","title":"Embracing the Generative AI Revolution: Advancing Tertiary Education in Cybersecurity with GPT","date":"2024-03-18","arxiv_id":"2403.11402","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-hokkien-dual-translation-by","slug":"enhancing-hokkien-dual-translation-by","title":"Enhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing Systems","date":"2024-03-18","arxiv_id":"2403.12024","n_code_links":1,"syntology":null},{"paper":"/paper/ensuring-safe-and-high-quality-outputs-a","slug":"ensuring-safe-and-high-quality-outputs-a","title":"Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models","date":"2024-03-18","arxiv_id":"2403.11838","n_code_links":1,"syntology":null},{"paper":null,"slug":"envgen-generating-and-adapting-environments","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","date":"2024-03-18","arxiv_id":"2403.12014","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","n_code_links":2,"syntology":null},{"paper":null,"slug":"gpt-4-as-evaluator-evaluating-large-language","title":"GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture","date":"2024-03-18","arxiv_id":"2403.11858","n_code_links":0,"syntology":null},{"paper":"/paper/hatecot-an-explanation-enhanced-dataset-for","slug":"hatecot-an-explanation-enhanced-dataset-for","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","date":"2024-03-18","arxiv_id":"2403.11456","n_code_links":1,"syntology":null},{"paper":null,"slug":"hiri-vit-scaling-vision-transformer-with-high","title":"HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs","date":"2024-03-18","arxiv_id":"2403.11999","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-are-we-on-the-decision-making-of-llms","slug":"how-far-are-we-on-the-decision-making-of-llms","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","date":"2024-03-18","arxiv_id":"2403.11807","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cuhk-arise/gamabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-prompting-for-automating-zero-shot","slug":"meta-prompting-for-automating-zero-shot","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","date":"2024-03-18","arxiv_id":"2403.11755","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jmiemirza/meta-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metaphor-understanding-challenge-dataset-for","title":"Metaphor Understanding Challenge Dataset for LLMs","date":"2024-03-18","arxiv_id":"2403.11810","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-feature-or-structured-feature-a","slug":"narrative-feature-or-structured-feature-a","title":"Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure","date":"2024-03-18","arxiv_id":"2403.11425","n_code_links":1,"syntology":null},{"paper":"/paper/regennet-towards-human-action-reaction","slug":"regennet-towards-human-action-reaction","title":"ReGenNet: Towards Human Action-Reaction Synthesis","date":"2024-03-18","arxiv_id":"2403.11882","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":5,"n_instrument":3,"unverified":3,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["liangxuy/ReGenNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semantic-enhanced-representation-learning-for","title":"Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics","date":"2024-03-18","arxiv_id":"2403.11495","n_code_links":0,"syntology":null},{"paper":null,"slug":"shifting-the-lens-detecting-malware-in-npm","title":"Leveraging Large Language Models to Detect npm Malicious Packages","date":"2024-03-18","arxiv_id":"2403.12196","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-the-relationship","title":"Towards Understanding the Relationship between In-context Learning and Compositional Generalization","date":"2024-03-18","arxiv_id":"2403.11834","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-semantic-enhanced-denoising","slug":"adaptive-semantic-enhanced-denoising","title":"Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution","date":"2024-03-17","arxiv_id":"2403.11078","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-uncertainty-leveraging-llms-to","title":"Aligning Uncertainty: Leveraging LLMs to Analyze Uncertainty Transfer in Text Summarization","date":"2024-03-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/correcting-misinformation-on-social-media","slug":"correcting-misinformation-on-social-media","title":"Correcting misinformation on social media with a large language model","date":"2024-03-17","arxiv_id":"2403.11169","n_code_links":1,"syntology":null},{"paper":"/paper/data-is-all-you-need-finetuning-llms-for-chip","slug":"data-is-all-you-need-finetuning-llms-for-chip","title":"Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework","date":"2024-03-17","arxiv_id":"2403.11202","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aichipdesign/chipgptft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"flowmind-automatic-workflow-generation-with","title":"FlowMind: Automatic Workflow Generation with LLMs","date":"2024-03-17","arxiv_id":"2404.13050","n_code_links":0,"syntology":null},{"paper":null,"slug":"forging-the-forger-an-attempt-to-improve","title":"Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation","date":"2024-03-17","arxiv_id":"2403.11265","n_code_links":0,"syntology":null},{"paper":null,"slug":"humsum-a-personalized-lecture-summarization","title":"HumSum: A Personalized Lecture Summarization Tool for Humanities Students Using LLMs","date":"2024-03-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/is-mamba-effective-for-time-series","slug":"is-mamba-effective-for-time-series","title":"Is Mamba Effective for Time Series Forecasting?","date":"2024-03-17","arxiv_id":"2403.11144","n_code_links":1,"syntology":null},{"paper":"/paper/jora-jax-tensor-parallel-lora-library-for","slug":"jora-jax-tensor-parallel-lora-library-for","title":"JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning","date":"2024-03-17","arxiv_id":"2403.11366","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-prompt-experts-for-multi-modal","title":"Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding","date":"2024-03-17","arxiv_id":"2403.11311","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-in-transformers-mitigating-spurious","title":"Reasoning in Transformers - Mitigating Spurious Correlations and Reasoning Shortcuts","date":"2024-03-17","arxiv_id":"2403.11314","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-wavelet-transformer","slug":"spiking-wavelet-transformer","title":"Spiking Wavelet Transformer","date":"2024-03-17","arxiv_id":"2403.11138","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["bic-l/spiking-wavelet-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-large-language-models-understand-medical","title":"Can Large Language Models abstract Medical Coded Language?","date":"2024-03-16","arxiv_id":"2403.10822","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-melting-pots-to-misrepresentations","title":"From Melting Pots to Misrepresentations: Exploring Harms in Generative AI","date":"2024-03-16","arxiv_id":"2403.10776","n_code_links":0,"syntology":null},{"paper":"/paper/from-words-to-routes-applying-large-language","slug":"from-words-to-routes-applying-large-language","title":"Can Large Language Models Solve Robot Routing?","date":"2024-03-16","arxiv_id":"2403.10795","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-powered-chatbots-for","title":"Large language model-powered chatbots for internationalizing student support in higher education","date":"2024-03-16","arxiv_id":"2403.14702","n_code_links":0,"syntology":null},{"paper":"/paper/pointer-generator-networks-for-low-resource","slug":"pointer-generator-networks-for-low-resource","title":"Pointer-Generator Networks for Low-Resource Machine Translation: Don't Copy That!","date":"2024-03-16","arxiv_id":"2403.10963","n_code_links":1,"syntology":null},{"paper":null,"slug":"retmil-retentive-multiple-instance-learning","title":"RetMIL: Retentive Multiple Instance Learning for Histopathological Whole Slide Image Classification","date":"2024-03-16","arxiv_id":"2403.10858","n_code_links":0,"syntology":null},{"paper":"/paper/time-series-representation-learning-with","slug":"time-series-representation-learning-with","title":"Time Series Representation Learning with Supervised Contrastive Temporal Transformer","date":"2024-03-16","arxiv_id":"2403.10787","n_code_links":1,"syntology":null},{"paper":null,"slug":"twin-transformer-using-gated-dynamic","title":"Twin Transformer using Gated Dynamic Learnable Attention mechanism for Fault Detection and Diagnosis in the Tennessee Eastman Process","date":"2024-03-16","arxiv_id":"2403.10842","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-robustness-of-visual-state","slug":"understanding-robustness-of-visual-state","title":"Understanding Robustness of Visual State Space Models for Image Classification","date":"2024-03-16","arxiv_id":"2403.10935","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-thorough-comparison-of-cross-encoders-and","title":"A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE","date":"2024-03-15","arxiv_id":"2403.10407","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-gpt-language-models-for","title":"Application of GPT Language Models for Innovation in Activities in University Teaching","date":"2024-03-15","arxiv_id":"2403.14694","n_code_links":0,"syntology":null},{"paper":"/paper/attention-enhanced-hybrid-feature-aggregation","slug":"attention-enhanced-hybrid-feature-aggregation","title":"Attention-Enhanced Hybrid Feature Aggregation Network for 3D Brain Tumor Segmentation","date":"2024-03-15","arxiv_id":"2403.09942","n_code_links":1,"syntology":null},{"paper":"/paper/dragin-dynamic-retrieval-augmented-generation","slug":"dragin-dynamic-retrieval-augmented-generation","title":"DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models","date":"2024-03-15","arxiv_id":"2403.10081","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["oneal2000/dragin"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-llm-factual-accuracy-with-rag-to","slug":"enhancing-llm-factual-accuracy-with-rag-to","title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","date":"2024-03-15","arxiv_id":"2403.10446","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["anlp-team/LTI_Neural_Navigator"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exegpt-constraint-aware-resource-scheduling","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","date":"2024-03-15","arxiv_id":"2404.07947","n_code_links":0,"syntology":null},{"paper":null,"slug":"fbpt-a-fully-binary-point-transformer","title":"FBPT: A Fully Binary Point Transformer","date":"2024-03-15","arxiv_id":"2403.09998","n_code_links":0,"syntology":null},{"paper":"/paper/generative-region-language-pretraining-for","slug":"generative-region-language-pretraining-for","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","date":"2024-03-15","arxiv_id":"2403.10191","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["foundationvision/generateu"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-powerful-potential-of-attention-on-image","title":"How Powerful Potential of Attention on Image Restoration?","date":"2024-03-15","arxiv_id":"2403.10336","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-condensation-and-reasoning-for","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","date":"2024-03-15","arxiv_id":"2403.10037","n_code_links":0,"syntology":null},{"paper":"/paper/magic-tokens-select-diverse-tokens-for-multi","slug":"magic-tokens-select-diverse-tokens-for-multi","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","date":"2024-03-15","arxiv_id":"2403.10254","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":9,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["924973292/editor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"medpnet-achieving-high-precision-adaptive","title":"MEDPNet: Achieving High-Precision Adaptive Registration for Complex Die Castings","date":"2024-03-15","arxiv_id":"2403.09996","n_code_links":0,"syntology":null},{"paper":null,"slug":"pasta-towards-flexible-and-efficient-hdr","title":"PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment","date":"2024-03-15","arxiv_id":"2403.10376","n_code_links":0,"syntology":null},{"paper":"/paper/raft-adapting-language-model-to-domain","slug":"raft-adapting-language-model-to-domain","title":"RAFT: Adapting Language Model to Domain Specific RAG","date":"2024-03-15","arxiv_id":"2403.10131","n_code_links":1,"syntology":null},{"paper":null,"slug":"repoformer-selective-retrieval-for-repository","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","date":"2024-03-15","arxiv_id":"2403.10059","n_code_links":0,"syntology":null},{"paper":null,"slug":"rough-transformers-for-continuous-and","title":"Rough Transformers for Continuous and Efficient Time-Series Modelling","date":"2024-03-15","arxiv_id":"2403.10288","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparsefusion-efficient-sparse-multi-modal","title":"SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception","date":"2024-03-15","arxiv_id":"2403.10036","n_code_links":0,"syntology":null},{"paper":"/paper/swinmtl-a-shared-architecture-for","slug":"swinmtl-a-shared-architecture-for","title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","date":"2024-03-15","arxiv_id":"2403.10662","n_code_links":1,"syntology":null},{"paper":null,"slug":"vitcn-vision-transformer-contrastive-network","title":"ViTCN: Vision Transformer Contrastive Network For Reasoning","date":"2024-03-15","arxiv_id":"2403.09962","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-continued-pretrained-llm-approach-for","title":"A Continued Pretrained LLM Approach for Automatic Medical Note Generation","date":"2024-03-14","arxiv_id":"2403.09057","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-on-ai-exploring-the-utility-of-gpt-as-an","title":"AI on AI: Exploring the Utility of GPT as an Expert Annotator of AI Publications","date":"2024-03-14","arxiv_id":"2403.09097","n_code_links":0,"syntology":null},{"paper":null,"slug":"aratrust-an-evaluation-of-trustworthiness-for","title":"AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic","date":"2024-03-14","arxiv_id":"2403.09017","n_code_links":0,"syntology":null},{"paper":"/paper/circuit-transformer-end-to-end-circuit-design","slug":"circuit-transformer-end-to-end-circuit-design","title":"Circuit Transformer: A Transformer That Preserves Logical Equivalence","date":"2024-03-14","arxiv_id":"2403.13838","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["snowkylin/circuit-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/codeultrafeedback-an-llm-as-a-judge-dataset","slug":"codeultrafeedback-an-llm-as-a-judge-dataset","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","date":"2024-03-14","arxiv_id":"2403.09032","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["martin-wey/codeultrafeedback"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-llms-for-gender-disparities-in","title":"Evaluating LLMs for Gender Disparities in Notable Persons","date":"2024-03-14","arxiv_id":"2403.09148","n_code_links":0,"syntology":null},{"paper":"/paper/fisher-mask-nodes-for-language-model-merging","slug":"fisher-mask-nodes-for-language-model-merging","title":"Fisher Mask Nodes for Language Model Merging","date":"2024-03-14","arxiv_id":"2403.09891","n_code_links":1,"syntology":null},{"paper":"/paper/git-towards-generalist-vision-transformer","slug":"git-towards-generalist-vision-transformer","title":"GiT: Towards Generalist Vision Transformer through Universal Language Interface","date":"2024-03-14","arxiv_id":"2403.09394","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-graph-attention-mechanism-into-1","slug":"incorporating-graph-attention-mechanism-into-1","title":"Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.14690","n_code_links":1,"syntology":null},{"paper":null,"slug":"komodo-a-linguistic-expedition-into-indonesia","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","date":"2024-03-14","arxiv_id":"2403.09362","n_code_links":0,"syntology":null},{"paper":"/paper/lamp-a-language-model-on-the-map","slug":"lamp-a-language-model-on-the-map","title":"LAMP: A Language Model on the Map","date":"2024-03-14","arxiv_id":"2403.09059","n_code_links":1,"syntology":null},{"paper":null,"slug":"leap-molecular-synthesisability-scoring-with","title":"Leap: molecular synthesisability scoring with intermediates","date":"2024-03-14","arxiv_id":"2403.13005","n_code_links":0,"syntology":null},{"paper":"/paper/optimistic-verifiable-training-by-controlling","slug":"optimistic-verifiable-training-by-controlling","title":"Optimistic Verifiable Training by Controlling Hardware Nondeterminism","date":"2024-03-14","arxiv_id":"2403.09603","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":4,"n_instrument":5,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["meghabyte/verifiable-training"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"d9d9421340916a548338a00095794544b184b469f58cf28586900534a899f66c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}